Road obstacle detection and tracking by an active and intelligent sensing strategy

In this paper, we address the problem of road obstacle deletion. We propose a method based on an active and intelligent sensing strategy. A sensor composed of a range finder coupled with a (charge-coupled-device) CCD camera is used. This sensor is mounted in front of a vehicle. The basic idea is first to determine 2D visual targets in intensity images of the camera. Then the range finder will be used not only to confirm or reject the existence of the detected visual targets, but also to acquire 3D information of the confirmed visual targets. The central problem of this strategy is how to detect 2D visual targets from intensity images of a road scene. In our method, we consider line segments as significant features. We use the concept ofline segment of interest and the concept ofdominant line segment. With the help of the identified dominant line segments in an image, we can effectively ascertain 2D visual targets. Finally, we use the range finder to confirm or reject a 2D visual target. A confirmed visual target is temporally tracked with the help of the range finder.

[1]  Matthew Turk,et al.  VITS-A Vision System for Autonomous Land Vehicle Navigation , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Peter J. Burt,et al.  Smart sensing within a pyramid vision machine , 1988, Proc. IEEE.

[3]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[4]  Giorgio Quaglia,et al.  The use of perceptual organization in the prediction of geometric structures , 1992, Pattern Recognit. Lett..

[5]  Tieniu Tan,et al.  Structure from Motion Using the Ground Plane Constraint , 1992, ECCV.

[6]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[7]  Geoffrey D. Sullivan,et al.  Model based perspective inversion , 1989, Image Vis. Comput..

[8]  Geoffrey D. Sullivan,et al.  Consistent labelling of image features using an assumption-based truth maintenance system , 1989, Image Vis. Comput..

[9]  Ernst D. Dickmanns,et al.  Recursive 3-D Road and Relative Ego-State Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Richard O. Duda,et al.  Use of Range and Reflectance Data to Find Planar Surface Regions , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[12]  Daniel DeMenthon,et al.  Range-video fusion and comparison of inverse perspective algorithms in static images , 1990, IEEE Trans. Syst. Man Cybern..

[13]  O DudaRichard,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972 .

[14]  Jake K. Aggarwal,et al.  Experiments in Intensity Guided Range Sensing Recognition of Three-Dimensional Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Anil K. Jain,et al.  Range-intensity histogram for segmenting LADAR images , 1992, Pattern Recognit. Lett..

[16]  Takeo Kanade,et al.  Autonomous land vehicle project at CMU , 1986, CSC '86.

[17]  Jake K. Aggarwal,et al.  Experiments in combining intensity and range edge maps , 1983, Comput. Vis. Graph. Image Process..

[18]  Monique Thonnat,et al.  An algorithm for finding closed curves , 1992, Pattern Recognit. Lett..

[19]  Werner von Seelen,et al.  Intensity and Edge-Based Symmetry Detection Applied to Car-Following , 1992, ECCV.

[20]  Takeo Kanade,et al.  Vision and Navigation for the Carnegie-Mellon Navlab , 1987 .

[21]  Hans-Hellmut Nagel,et al.  Model-Based Object Tracking in Traffic Scenes , 1992, ECCV.

[22]  I. Masaki,et al.  Vision-based vehicle guidance , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.